About the role
<div class="content-intro"><p>We fuse together exceptional talent who deliver outstanding software solutions. Our approach has helped us grow 60% in 2021, 94% in 2022, while in 2023 we joined forces with Insight, a Fortune 500 company and a leading solutions and systems integrator. With exciting growth plans and cutting-edge projects, there has never been a better time to join our incredible team.&nbsp;</p></div><h5 style="font-weight: 600; padding-top: 2.75rem;">About the Project</h5> <p class="p-large" style="font-weight: 400;">We are building production-grade agentic content workflows for English Language Learning at Pearson. The platform uses AI agent architectures to generate and validate educational content at scale, serving multiple products across the organization. The team owns the end-to-end lifecycle: workflow design, LLM orchestration, evaluation, and production operations.</p> <h5 style="font-weight: 600; padding-top: 2.75rem;">About the Role</h5> <p class="p-large" style="font-weight: 400;">We are looking for a senior AI engineer ready to work at the heart of production AI systems. You will contribute directly to two core services: Conversation Brain, an LLM-driven conversation engine, and Ambient ORA, a speech assessment engine powering multiple products across Pearson. The role sits at the intersection of product engineering and AI science, bridging research outputs from the R&amp;D team into production-grade services.</p> <h5 style="font-weight: 600; padding-top: 2.75rem;">Key Responsibilities</h5> <ul> <li class="p-large" style="font-weight: 400;">Design, develop, and optimize AI-driven content generation workflows.</li> <li class="p-large" style="font-weight: 400;">Contribute directly to our codebases, building and maintaining agentic workflows using Python (FastAPI, CrewAI, LangGraph, LangChain) and Go where needed.</li> <li class="p-large" style="font-weight: 400;">Build and maintain agentic workflows using CrewAI, LangGraph, and LangChain.</li> <li class="p-large" style="font-weight: 400;">Ensure code quality through unit and integration tests written as part of the development workflow, in line with our shift-left approach where developers own test creation.</li> <li class="p-large" style="font-weight: 400;">Operationalize AI models in collaboration with the AI R&amp;D.</li> <li class="p-large" style="font-weight: 400;">Implement LLM observability and evaluation using Langfuse, OpenLit, and New Relic.</li> <li class="p-large" style="font-weight: 400;">Design and run LLM evaluation benchmarks and regression detection.</li> <